agent-browser
claudeSkills for browser automation with agent-browser CLI, Playwright test generation, and web debugging workflows
3 skills
[Experimental] One node of a contract tree — do a contract yourself or split it into sub-contracts you write, dispatch them, route what comes back, report up in a fixed shape; narrows a question that is not yet a contract first
Plugin method from marketplace nick-personal-marketplace in musingfox/cc-plugins. Commands read from the repo's manifest — 5 days ago.
methodRun a goal as one node of a contract tree: do it yourself or split it into sub-contracts you write, dispatch them, route what comes back, and report up in a fixed shape. Use when a goal's scope is settled and it should be built, or when the user is not yet sure what to build (\"help me think this th
divergenceDivergence role — the widening motion: given a question and the human's feedback so far, name the distinct directions it could go and what each one commits to. Lists possibilities; never implements. Invoked by the node narrowing the question.
probeProbe role — a shallow, throwaway descent down ONE candidate direction, run only to find what it collides with. Reports the collision, never a plan and never a recommendation. Invoked in parallel by the node narrowing the question, one per live candidate.
prototypePrototype role — builds and runs ONE throwaway thing to answer a design question the reasoning could not settle, then reports the verdict. Never a plan, never a recommendation; the code is evidence and lives on a branch nobody merges. Invoked by the node narrowing the question when a probe cannot re
reviewVerify a builder's diff against the pinned contracts
Skills for browser automation with agent-browser CLI, Playwright test generation, and web debugging workflows
3 skills
[Experimental] Repository audits that put each piece of knowledge where it cannot drift — the repo's docs, from README to CLAUDE.md, sorted into what is a cache of the code, a rule or a decision, and its standing milestones' commitments traced to the tests that guard them
1 skill · 2 agents
Survey a codebase for deepening opportunities — shallow modules, leaking seams, interfaces that are hard to test through — and hand the candidates to viz as a Mermaid report
1 skill · 1 agent
Diagnose a confirmed cause of a bug and leave one failing test on a branch to read from, without applying the fix
2 skills
Obsidian Workspace — project-scoped vault project management. /obw:pm is the one command: it owns setup, folder layout and templates, files tasks and docs under pm/<project>/ by their content, and splits a spec into blocking tickets; /issue is a Claude Mod pane that lists a view of the project's dashboard, draws Mermaid as text diagrams, and can open a card in the browser through viz. Vault I/O uses the Obsidian CLI via the official obsidian-cli skill.
1 skill · hooks
[Experimental] Offload heavy work to cheap/fast models via pi — background dispatch + idempotent poll + worktree isolation, so Claude only issues briefs, reviews results, and scales to parallel tasks while saving tokens
1 skill · 1 agent
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Use Alibaba Open Code Review from local Codex.
2 skills
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Use Codex from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work with both LanceDB Embedded and LanceDB Enterprise.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.